Publication: A new learning strategy for stereo matching derived from a fuzzy clustering method
Loading...
Official URL
Full text at PDC
Publication Date
2000-03-16
Advisors (or tutors)
Editors
Journal Title
Journal ISSN
Volume Title
Publisher
Elsevier Science BV
Citations
Exportar
Abstract
This paper presents an approach to the local stereo correspondence problem. The primitives or features used are groups of collinear connected edge points called segments. Each segment has several associated attributes or properties. We have verified that the differences of the attributes for the true matches cluster in a cloud around a center. Then for each current pair of primitives we compute a distance between the difference of its attributes and the cluster center. The correspondence is established in the basis of the minimum distance criterion (similarity constraint). We have designed an image understanding system to learn the best representative cluster center. For such purpose a new learning method is derived from the Fuzzy c-Means (FcM) algorithm where the dispersion of the true samples in the cluster is taken into account through the Mahalanobis distance. This is the main contribution of this paper. A better performance of the proposed local stereo-matching learning method is illustrated with a comparative analysis between classical local methods without learning.
Description
© Elsevier Science BV.
The authors wish to acknowledge Prof. Dr. S. Dormido, Head of Department of Informática y Automática, CC Físicas, UNED, Madrid, for his support and encouragement. Part of this work has been performed under project CICYT TAP94-0832-C02-01. The constructive recommendations provided by the reviewers are also gratefully acknowledged.
UCM subjects
Unesco subjects
Keywords
Citation
[1] N. Ayache, B. Faverjon, Efficient registration of stereo images by matching graph descriptions of edge segments, Int. J. Computer Vision 1 (1987) 107-131.
[2] H.H. Baker, Building and using scene representations in image understanding, AGARD-LS-185 Machine Perception (1992) 3.1-3.11.
[3] J.C. Bezdek, R.J. Hathaway, M.J. Sabin, W.T. Tucker, Convergence theory for fuzzy c-means: counterexamples and repairs, IEEE Trans. System Man Cybernet. 17(5) (1987) 873-877.
[4] J.C. Bezdek, Pattern Recognition with Fuzzy Objective Function Algorithms, Plenum Press, New York, 1981.
[5] A.W. Biermann, K.C. Gilbert, A.F. Fahmy, B. Koster, On the errors that learning machines will make, Int. J. Intelligent Systems 9 (1994) 269-302.
[6] T.M. Breuel, Finding lines under bounded error, Pattern Recognition 29 (1) (1996) 167-178.
[7] D. Chaudhuri, C.A. Murthy, B.B. Chaudhuri, A modi_ed metric to compute distance, Pattern Recognition 25 (7) (1992) 667-677.
[8] J.M. Cruz, G. Pajares, J. Aranda, A neural network approach to the stereovision correspondence problem by unsupervised learning, Neural Networks 8 (6) (1995) 805-813.
[9] J.M. Cruz, G. Pajares, J. Aranda, J.L.F. Vindel, Stereo matching technique based on the perceptron criterion function, Pattern Recognition Lett. 16 (1995) 933-944.
[10] A.R. Dhond, J.K. Aggarwal, Structure from stereo a review, IEEE Trans. System Man Cybernet. 19 (1989) 1489-1510.
[11] R.O. Duda, P.E. Hart, Pattern Classfication and Scene Analysis, Wiley, New York, 1989.
[12] E. Fernandez, Relaxation labeling algorithm based on learning automata, in: N. Perez de la Blanca, A. Sanfeliu, E. Vidal (Eds.), Pattern Recognition and Image Analysis, World Scientfic, Singapore, 1992, pp. 3-20.
[13] P. Fua, A parallel algorithm that produces dense depth maps and preserves image features, Machine Vision Appl. 6 (1993) 35-49.
[14] K.S. Fu, R.C. González, C.S.G. Lee, Robótica: Control, detección, visión e inteligencia, McGraw-Hill, Madrid, 1988.
[15] W.E.L. Grimson, Computational experiments with a featurebased stereo algorithm, IEEE Trans. Pattern Anal. Mach. Intell. 7 (1985) 17-34.
[16] S. Haykin, Neural Networks: A Comprehensive Foundation, Macmillan, New York, 1994.
[17] W. H0ff, N. Ahuja, Surface from stereo: integrating feature matching, disparity estimation, and contour detection, IEEE Trans. Pattern Anal. Mach. Intell. 11 (1989) 121-136.
[18] A. Huertas, G. Medioni, Detection of intensity changes with subpixel accuracy using Laplacian{Gaussian masks, IEEE Trans. Pattern Anal. Mach. Intell. 8 (5) (1986) 651-664.
[19] M.S. Kamel, S.Z. Selim, A relaxation approach to the fuzzy clustering problem, Fuzzy Sets and Systems 61 (1994) 177-188.
[20] M.S. Kamel, S.Z. Selim, New algorithms for solving the fuzzy clustering problem, Pattern Recognition 27 (3) (1994) 421-428.
[21] A. Khotanzad, A. Bokil, Y.W. Lee, Stereopsis by constraint learning feed-forward neural networks, IEEE Trans. Neural Networks 4 (1993) 332-342.
[22] D.H. Kim, J.K. Aggarwal, Positioning three-dimensional objects using stereo images, IEEE J. Robotics Automat. 3 (1987) 361-373.
[23] D.H. Kim, W.Y. Choi, R.H. Park, Stereo matching technique based on the theory of possibility, Pattern Recognition Lett. 13 (1993) 735-744.
[24] D.H. Kim, R.H. Park, Analysis of quantization error in line-based stereo matching, Pattern Recognition 7 (1994) 913-924.
[25] B. Kosko, Neural Networks and Fuzzy Systems, Prentice-Hall, Englewood Cliffs, NJ, 1992.
[26] E.P. Krotkov, Active Computer Vision by Cooperative Focus and Stereo, Springer, New York, 1989.
[27] S.H. Lee, J.J. Leou, A dynamic programming approach to line segment matching in stereo vision, Pattern Recognition 27 (1994) 961-986.
[28] J.G. Leu, H.L. Yau, Detecting the dislocations in metal crystals from microscopic images, Pattern Recognition 24 (1)(1991) 41-56.
[29] M.S. Lew, T.S. Huang, K. Wong, Learning and feature selection in stereo matching, IEEE Trans. Pattern Anal. Mach. Intell. 16 (9) (1994) 869-881.
[30] V.R. Lutsiv, T.A. Novikova, On the use of a neurocomputer for stereoimage processing, Pattern Recognition Image Anal. 2 (1992) 441-444.
[31] D. Maravall, E. Fernandez, Contribution to the matching problem in stereovision, Proc. 11th IAPR: Internat. Conf. on Pattern Recognition, 1992, pp. 411-414.
[32] D. Maravall, Reconocimiento de Formas y Vision Artificial, RA-MA, Madrid, 1993.
[33] D. Marr, Vision, Freeman, San Francisco, 1982.
[34] D. Marr, T. Poggio, A computational theory of human stereovision, Proc. Roy. Soc. London B 207 (1979) 301-328.
[35] D. Marr, T. Poggio, Cooperative computation of stereo disparity, Science 194 (1976) 283-287.
[36] G. Medioni, R. Nevatia, Segment based stereo matching, Comput. Vision Graphics Image Process. 31 (1985) 2-18.
[37] R. Nevatia, K.R. Babu, Linear feature extraction and description, Comput. Vision Graphics Image Process. 13 (1980) 257-269.
[38] T. Ozanian, Approaches for Stereo matching - a review, Modeling Identification Control 16 (2) (1995) 65-94.
[39] G. Pajares, Estrategia de Solucion al Problema de la Correspondencia en Visión Estereoscópica por la Jerarquía Metodológica y la Integración de Criterios, Thesis, Madrid Dpto. Informática y Automática, Facultad Ciencias, 1995.
[40] G. Pajares, R. Pereira, J. Rives, J.A. Diaz, Correspondencia Difusa en visión Estereoscópica, in: S. Barro, A. Sobrino (Eds.), III Congreso Español Sobre Tecnologías y Lógica Fuzzy, Santiago de Compostela, 1993, pp. 303-310.
[41] S.B. Pollard, J.E.W. Mayhew, J.P. Frisby, PMF: a stereo correspondence algorithm using a disparity gradient limit, Perception 14 (1981) 449-470.
[42] K. Prazdny, Detection of binocular disparities, Biol. Cybernet. 52 (1985) 93-99.
[43] F. Rhodes, On the metrics of Chauduri, Murthy and Chauduri, Pattern Recognition 28 (5) (1995) 745-752.
[44] P. Rubio, RP: un algoritmo efciente para la búsqueda de correspondencias en visión estereoscópica, Informática y Automática 26 (1993) 5-15.
[45] S.Z. Selim, M.S. Kamel, On the mathematical and numerical properties of the Fuzzy c-Means Algorithm, Fuzzy Sets and Systems 49 (1992) 181-191.
[46] Y. Shirai, Three-Dimensional Computer Vision, Springer, Berlin, 1983.
[47] S. Tanaka, A.C. Kak, A rule-based approach to binocular stereopsis, in: R.C. Jain, A.K. Jain (Eds.), Analysis and Interpretation of Range Images, Springer, Berlin, 1990, pp. 33-139.
[48] E.C.K. Tsao, W.C. Lin, C.T. Chen, Constraint satisfaction neural networks for image recognition, Pattern Recognition 26 (1993) 553-567.
[49] H.F. Wang, C. Wang, G.Y. Wu, Bi-criteria Fuzzy c-Means analysis, Fuzzy Sets and Systems 64 (1994) 311-319.
[50] M.P. Windham, Cluster validity for fuzzy clustering algorithms, Fuzzy Sets and Systems 5 (1981) 177-185.
[51] M.P. Windham, Cluster validity for the Fuzzy c-Means clustering algorithm, IEEE Trans. Pattern Anal. Mach. Intell. 4 (1982) 357-363.
[52] D.M. Wuescher, K.L. Boyer, Robust contour decomposition using a constraint curvature criterion, IEEE Trans. Pattern Anal. Machine Intell. 13 (1) (1991) 41-51.
[53] Y. Zhou, R. Chellappa, Artificial Neural Networks for Computer Vision, Springer, New York, 1992.
[54] H.J. Zimmermann, Fuzzy Set Theory and its Applications, Kluwer Academic Publishers, Norwell, 1991.